Student Profile Modeling Using Boosting Algorithms

The student profile has become an important component of education systems. Many systems objectives, as e-recommendation, e-orientation, e-recruitment and dropout prediction are essentially based on the profile for decision support. Machine learning plays an important role in this context and several studies have been carried out either for classification, prediction or clustering purpose. In this paper, the authors present a comparative study between different boosting algorithms which have been used successfully in many fields and for many purposes. In addition, the authors applied feature selection methods Fisher Score, Information Gain combined with Recursive Feature Elimination to enhance the preprocessing task and models’ performances. Using multi-label dataset predict the class of the student performance in mathematics, this article results show that the Light Gradient Boosting Machine (LightGBM) algorithm achieved the best performance when using Information gain with Recursive Feature Elimination method compared to the other boosting algorithms.

Novel Machine Learning for Big Data Analytics in Intelligent Support Information Management Systems

Two-dimensional 1 arrays of bi-component structures made of cobalt and permalloy elliptical dots with thickness of 25 nm, length 1 mm and width of 225 nm, have been prepared by a self-aligned shadow deposition technique. Brillouin light scattering has been exploited to study the frequency dependence of thermally excited magnetic eigenmodes on the intensity of the external magnetic field, applied along the easy axis of the elements. Scientific information technology has been developed rapidly. Here, the purposes are to make people's lives more convenient and ensure information management and classification. The machine learning algorithm is improved to obtain the optimized Light Gradient Boosting Machine (LightGBM) algorithm. Then, an Android-based intelligent support information management system is designed based on LightGBM for the big data analysis and classification management of information in the intelligent support information management system. The system is designed with modules of employee registration and login, company announcement notice, attendance and attendance management, self-service, and daily tools with the company as the subject. Furthermore, the performance of the constructed information management system is analyzed through simulations. Results demonstrate that the training time of the optimized LightGBM algorithm can stabilize at about 100s, and the test time can stabilize at 0.68s. Besides, its accuracy rate can reach 89.24%, which is at least 3.6% higher than other machine learning algorithms. Moreover, the acceleration efficiency analysis of each algorithm suggests that the optimized LightGBM algorithm is suitable for processing large amounts of data; its acceleration effect is more apparent, and its acceleration ratio is higher than other algorithms. Hence, the constructed intelligent support information management system can reach a high accuracy while ensuring the error, with apparent acceleration effect. Therefore, this model can provide an experimental reference for information classification and management in various fields.

Degradation Trend Prediction of Pumped Storage Unit Based on MIC-LGBM and VMD-GRU Combined Model

The harsh operating environment aggravates the degradation of pumped storage units (PSUs). Degradation trend prediction (DTP) provides important support for the condition-based maintenance of PSUs. However, the complexity of the performance degradation index (PDI) sequence poses a severe challenge of the reliability of DTP. Additionally, the accuracy of healthy model is often ignored, resulting in an unconvincing PDI. To solve these problems, a combined DTP model that integrates the maximal information coefficient (MIC), light gradient boosting machine (LGBM), variational mode decomposition (VMD) and gated recurrent unit (GRU) is proposed. Firstly, MIC-LGBM is utilized to generate a high-precision healthy model. MIC is applied to select the working parameters with the most relevance, then the LGBM is utilized to construct the healthy model. Afterwards, a performance degradation index (PDI) is generated based on the LGBM healthy model and monitoring data. Finally, the VMD-GRU prediction model is designed to achieve precise DTP under the complex PDI sequence. The proposed model is verified by applying it to a PSU located in Zhejiang province, China. The results reveal that the proposed model achieves the highest precision healthy model and the best prediction performance compared with other comparative models. The absolute average (|AVG|) and standard deviation (STD) of fitting errors are reduced to 0.0275 and 0.9245, and the RMSE, MAE, and R2 are 0.00395, 0.0032, and 0.9226 respectively, on average for two operating conditions.

Short-Term Energy Forecasting Using Machine-Learning-Based Ensemble Voting Regression

Meeting the required amount of energy between supply and demand is indispensable for energy manufacturers. Accordingly, electric industries have paid attention to short-term energy forecasting to assist their management system. This paper firstly compares multiple machine learning (ML) regressors during the training process. Five best ML algorithms, such as extra trees regressor (ETR), random forest regressor (RFR), light gradient boosting machine (LGBM), gradient boosting regressor (GBR), and K neighbors regressor (KNN) are trained to build our proposed voting regressor (VR) model. Final predictions are performed using the proposed ensemble VR and compared with five selected ML benchmark models. Statistical autoregressive moving average (ARIMA) is also compared with the proposed model to reveal results. For the experiments, usage energy and weather data are gathered from four regions of Jeju Island. Error measurements, including mean absolute percentage error (MAPE), mean absolute error (MAE), and mean squared error (MSE) are computed to evaluate the forecasting performance. Our proposed model outperforms six baseline models in terms of the result comparison, giving a minimum MAPE of 0.845% on the whole test set. This improved performance shows that our approach is promising for symmetrical forecasting using time series energy data in the power system sector.

Machine Learning in Prediction of Bladder Cancer on Clinical Laboratory Data

Bladder cancer has been increasing globally. Urinary cytology is considered a major screening method for bladder cancer, but it has poor sensitivity. This study aimed to utilize clinical laboratory data and machine learning methods to build predictive models of bladder cancer. A total of 1336 patients with cystitis, bladder cancer, kidney cancer, uterus cancer, and prostate cancer were enrolled in this study. Two-step feature selection combined with WEKA and forward selection was performed. Furthermore, five machine learning models, including decision tree, random forest, support vector machine, extreme gradient boosting (XGBoost), and light gradient boosting machine (GBM) were applied. Features, including calcium, alkaline phosphatase (ALP), albumin, urine ketone, urine occult blood, creatinine, alanine aminotransferase (ALT), and diabetes were selected. The lightGBM model obtained an accuracy of 84.8% to 86.9%, a sensitivity 84% to 87.8%, a specificity of 82.9% to 86.7%, and an area under the curve (AUC) of 0.88 to 0.92 in discriminating bladder cancer from cystitis and other cancers. Our study provides a demonstration of utilizing clinical laboratory data to predict bladder cancer.

Estimation of Soil Salinization by Machine Learning Algorithms in Different Arid Regions of Northwest China

Hyperspectral data has attracted considerable attention in recent years due to its high accuracy in monitoring soil salinization. At present, most existing research focuses on the saline soil in a single area without comparative analysis between regions. The regional differences in the hyperspectral characteristics of saline soil are still unclear. Thus, we chose Golmud in the cold–dry Qaidam Basin (QB–G) and Gaotai–Minghua in the relatively warm–dry Hexi Corridor (HC–GM) as the study areas, and used the deep extreme learning machine (DELM) and sine cosine algorithm–Elman (SCA–Elman) to predict soil salinity, and then selected the most suitable algorithm in these two regions. A total of 79 (QB–G) and 86 (HC–GM) soil samples were collected and tested to obtain their electrical conductivity (EC) and corresponding hyperspectral reflectance (R). We utilized the land surface parameters that affect the soil based on Landsat 8 and digital elevation model (DEM) data, selected the variables using the light gradient boosting machine (LightGBM), and built SCA–Elman and DELM from the hyperspectral reflectance data combined with land surface parameters. The results revealed the following: (1) The soil hyperspectral reflectance in QB–G was higher than that in HC–GM. The soils of QB–G are mainly the chloride type and those of HC–GM mainly belong to the sulfate type, having lower reflectance. (2) The accuracies of some of the SCA–Elman and DELM models in QB–G (the highest MAEv, RMSEv, and were 0.09, 0.12 and 0.75, respectively) were higher than those in HC–GM (the highest MAEv, RMSEv, and were 0.10, 0.14 and 0.73, respectively), which has flatter terrain and less obvious surface changes. The surface parameters in QB–G had higher correlation coefficients with EC due to the regular altitude change and cold–dry climate. (3) Most of the SCA–Elman results (the mean in HC-GM and QB-G were 0.62 and 0.60, respectively) in all areas performed better than the DELM results (the mean in HC–GM and QB–G were 0.51 and 0.49, respectively). Therefore, SCA–Elman was more suitable for the soil salinity prediction in HC–GM and QB–G. This can provide a reference for soil salinization monitoring and model selection in the future.

Identifying the roots of inequality of opportunity in South Korea by application of algorithmic approaches

This study identifies the roots of inequality of opportunity in South Korea by applying algorithmic approaches to survey data. In contrast to extant studies, we identify the roots of inequality of opportunity by estimating the importance of variables, interpreting the estimated results, and analyzing the importance of individual variables, instead of measuring inequality of opportunity. We apply a decision tree classification algorithm, light gradient boosting machine, and SHapley Additive exPlanations to estimate the importance of the studied variables and interpret the estimated results. According to the estimated results, the region where the individuals grew up, their gender, and their father’s job during their childhood were the main factors contributing to inequality of opportunity. This study proves that the considerable regional disparity and social environment perpetuate gender inequality in South Korean society. It argues that an individual’s socio-economic achievements are strongly influenced by their father’s background, thus, outweighing other family background-related factors. Individuals receive unequal opportunities owing to a combination of region, father’s background, and their own gender, thereby, affecting their socioeconomic achievements. If these factors remain influential from birth to adulthood, removing the conditions that structure them would be one way to achieve equality of opportunity.

Towards Predicting 30-Day Readmission among Oncology Patients: Identifying Timely and Actionable Risk Factors

Purpose: Predicting 30-day readmission risk is paramount to improving the quality of patient care. Previous studies have examined clinical risk factors associated with hospital readmissions. In this study, we compare sets of patient, provider, and community-level variables that are available at two different points of a patient's inpatient encounter (first 48 hours and the full encounter) to train readmission prediction models in order to identify and target appropriate actionable interventions that can potentially reduce avoidable readmissions. Methods: Using EHR data from a retrospective cohort of 2460 oncology patients, two sets of binary classification models predicting 30-day readmission were developed; one trained on variables that are available within the first 48 hours of admission and another trained on data from the entire hospital encounter. A comprehensive machine learning analysis pipeline was leveraged including preprocessing and feature transformation, feature importance and selection, machine learning modeling, and post-analysis. Results: Leveraging all features, the LGB (light gradient boosted machines) model produced higher, but comparable performance: (AUC: 0.711 and APS: 0.225) compared to Epic (AUC: 0.697 and APS: 0.221). Given features in the first 48-hours, the random forest model produces higher AUC (0.684), but lower PRC (0.18) and APS (0.184) than the Epic model (AUC: 0.676). In terms of the characteristics of patients flagged by these models, both the full LGB and 48-hour (random forest) feature models were highly sensitive in flagging more patients than the Epic models. Both models flagged patients with a similar distribution of race and sex; however, our LGB and random forest models more inclusive flagging more patients among younger age groups. The Epic models were more sensitive to identifying patients with an average lower zip income. Our 48-hour models were powered by novel features at various levels: patient (weight changeover 365 days, depression symptoms, laboratory values, cancer type), provider (winter discharge, hospital admission type), community (zip income, marital status of partner). Conclusion: We demonstrated that we could develop and validate models comparable to existing Epic 30-day readmission models, but provide several actionable insights that could create service interventions deployed by the case management or discharge planning teams that may decrease readmission rates over time.

Artificial Intelligence for Risk Prediction of Rehospitalization with Acute Kidney Injury in Sepsis Survivors

Sepsis survivors have a higher risk of long-term complications. Acute kidney injury (AKI) may still be common among sepsis survivors after discharge from sepsis. Therefore, our study utilized an artificial-intelligence-based machine learning approach to predict future risks of rehospitalization with AKI between 1 January 2008 and 31 December 2018. We included a total of 23,761 patients aged ≥ 20 years who were admitted due to sepsis and survived to discharge. We adopted a machine learning method by using models based on logistic regression, random forest, extra tree classifier, gradient boosting decision tree (GBDT), extreme gradient boosting, and light gradient boosting machine (LGBM). The LGBM model exhibited the highest area under the receiver operating characteristic curves (AUCs) of 0.816 to predict rehospitalization with AKI in sepsis survivors and followed by the GBDT model with AUCs of 0.813. The top five most important features in the LGBM model were C-reactive protein, white blood cell counts, use of inotropes, blood urea nitrogen and use of diuretics. We established machine learning models for the prediction of the risk of rehospitalization with AKI in sepsis survivors, and the machine learning model may set the stage for the broader use of clinical features in healthcare.

Differential Effects of Lateral and Medial Entorhinal Cortex Lesions on Trace, Delay and Contextual Fear Memories

The entorhinal cortex (EC), with connections to the hippocampus, amygdala, and neocortex, is a critical, yet still underexplored, contributor to fear memory. Previous research suggests possible heterogeneity of function among its lateral (LEC) and medial (MEC) subregions. However, it is not well established what unique roles these subregions serve as the literature has shown mixed results depending on target of manipulation and type of conditioning used. Few studies have manipulated both the LEC and MEC within the same experiment. The present experiment systematically manipulated LEC and MEC function to examine their potential roles in fear memory expression. Long-Evans rats were trained using either trace or delay fear conditioning. The following day, rats received an N-methyl-D-aspartate (NMDA)-induced lesion to the LEC or MEC or received a sham surgery. Following recovery, rats were given an 8-min context test in the original context. The next day, rats were tested for tone freezing in a novel context with three discrete tone presentations. Further, rats were tested for hyperactivity in an open field under both dark and bright light gradient conditions. Results: Following either LEC or MEC lesion, freezing to context was significantly reduced in both trace and delay conditioned rats. LEC-lesioned rats consistently showed significantly less freezing following tone-offset (trace interval, or equivalent, and intertrial interval) in both trace and delay fear conditioned rats. Conclusions: These data suggest that the LEC may play a role in the expression of a conjunctive representation between the tone and context that mediates the maintenance of post-tone freezing.